BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Lei Zhu

Lei Zhu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine LearningInformation Retrievaleess.IVArtificial Intelligenceastro-ph.GAastro-ph.SRphysics.atom-phBiological Physicscond-mat.mes-hallCryptography and SecurityDatabaseseess.ASGraphicsphysics.opticsquant-phSoftware EngineeringSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
40works
0followers
18topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

40 published item(s)

preprint2026arXiv

A Flexible Adaptive Stable Clustering Algorithm for Archive-Scale Online Mass Spectrometry

Modern online mass spectrometry generates multi-terabyte data streams critical for understanding Earth's environmental systems. However, extracting actionable chemical insights from these repositories is impeded by a computational bottleneck: existing clustering methods force a compromise among scalability, metric flexibility, and algorithmic stability. Here, we introduce Flexible Adaptive Stable Clustering (FASC), a dynamical systems framework that resolves these constraints by architecturally decoupling the similarity kernel from rigorous optimization logic. Unlike legacy heuristics that suffer from stochastic drift and algorithmic blending, FASC employs a Density-Augmented Similarity Selection rule and geometric constraints to guarantee deterministic, order-independent convergence. After validating FASC on canonical machine-learning ground truths (achieving >99.5% cluster purity and 0.99 Adjusted Rand Index), we deployed the framework on 25 million mass spectra of atmospheric aerosols. Demonstrating strictly linear empirical runtime scaling (O(N)), FASC autonomously mapped atmospheric aging pathways of secondary inorganic aerosols while isolating ultra-rare industrial tracers (<0.2% abundance), providing a scalable infrastructure for mining environmental big data.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model

Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem. But the performance has been found usually limited due to heavy reliance on environmental assumption. In this paper, we propose a unified multichannel far-field speech recognition system that combines the neural beamforming and transformer-based Listen, Spell, Attend (LAS) speech recognition system, which extends the end-to-end speech recognition system further to include speech enhancement. Such framework is then jointly trained to optimize the final objective of interest. Specifically, factored complex linear projection (fCLP) has been adopted to form the neural beamforming. Several pooling strategies to combine look directions are then compared in order to find the optimal approach. Moreover, information of the source direction is also integrated in the beamforming to explore the usefulness of source direction as a prior, which is usually available especially in multi-modality scenario. Experiments on different microphone array geometry are conducted to evaluate the robustness against spacing variance of microphone array. Large in-house databases are used to evaluate the effectiveness of the proposed framework and the proposed method achieve 19.26\% improvement when compared with a strong baseline.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector

Out-of-distribution (OOD) detection plays a crucial role in ensuring the security of neural networks. Existing works have leveraged the fact that In-distribution (ID) samples form a subspace in the feature space, achieving state-of-the-art (SOTA) performance. However, the comprehensive characteristics of the ID subspace still leave under-explored. Recently, the discovery of Neural Collapse ($\mathcal{NC}$) sheds light on novel properties of the ID subspace. Leveraging insight from $\mathcal{NC}$, we observe that the Principal Angle between the features and the ID feature subspace forms a superior representation for measuring the likelihood of OOD. Building upon this observation, we propose a novel $\mathcal{NC}$-inspired OOD scoring function, named Entropy-enhanced Principal Angle (EPA), which integrates both the global characteristic of the ID subspace and its inner property. We experimentally compare EPA with various SOTA approaches, validating its superior performance and robustness across different network architectures and OOD datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos

Breast lesion detection in ultrasound is critical for breast cancer diagnosis. Existing methods mainly rely on individual 2D ultrasound images or combine unlabeled video and labeled 2D images to train models for breast lesion detection. In this paper, we first collect and annotate an ultrasound video dataset (188 videos) for breast lesion detection. Moreover, we propose a clip-level and video-level feature aggregated network (CVA-Net) for addressing breast lesion detection in ultrasound videos by aggregating video-level lesion classification features and clip-level temporal features. The clip-level temporal features encode local temporal information of ordered video frames and global temporal information of shuffled video frames. In our CVA-Net, an inter-video fusion module is devised to fuse local features from original video frames and global features from shuffled video frames, and an intra-video fusion module is devised to learn the temporal information among adjacent video frames. Moreover, we learn video-level features to classify the breast lesions of the original video as benign or malignant lesions to further enhance the final breast lesion detection performance in ultrasound videos. Experimental results on our annotated dataset demonstrate that our CVA-Net clearly outperforms state-of-the-art methods. The corresponding code and dataset are publicly available at \url{https://github.com/jhl-Det/CVA-Net}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

B-fields in Star-Forming Region Observations (BISTRO): Magnetic Fields in the Filamentary Structures of Serpens Main

We present 850 $μ$m polarimetric observations toward the Serpens Main molecular cloud obtained using the POL-2 polarimeter on the James Clerk Maxwell Telescope (JCMT) as part of the B-fields In STar-forming Region Observations (BISTRO) survey. These observations probe the magnetic field morphology of the Serpens Main molecular cloud on about 6000 au scales, which consists of cores and six filaments with different physical properties such as density and star formation activity. Using the histogram of relative orientation (HRO) technique, we find that magnetic fields are parallel to filaments in less dense filamentary structures where $N_{H_2} < 0.93\times 10^{22}$ cm$^{-2}$ (magnetic fields perpendicular to density gradients), while being perpendicular to filaments (magnetic fields parallel to density gradients) in dense filamentary structures with star formation activity. Moreover, applying the HRO technique to denser core regions, we find that magnetic field orientations change to become perpendicular to density gradients again at $N_{H_2} \approx 4.6 \times 10^{22}$ cm$^{-2}$. This can be interpreted as a signature of core formation. At $N_{H_2} \approx 16 \times 10^{22}$ cm$^{-2}$ magnetic fields change back to being parallel to density gradients once again, which can be understood to be due to magnetic fields being dragged in by infalling material. In addition, we estimate the magnetic field strengths of the filaments ($B_{POS} = 60-300~μ$G)) using the Davis-Chandrasekhar-Fermi method and discuss whether the filaments are gravitationally unstable based on magnetic field and turbulence energy densities.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization

Classification activation map (CAM), utilizing the classification structure to generate pixel-wise localization maps, is a crucial mechanism for weakly supervised object localization (WSOL). However, CAM directly uses the classifier trained on image-level features to locate objects, making it prefers to discern global discriminative factors rather than regional object cues. Thus only the discriminative locations are activated when feeding pixel-level features into this classifier. To solve this issue, this paper elaborates a plug-and-play mechanism called BagCAMs to better project a well-trained classifier for the localization task without refining or re-training the baseline structure. Our BagCAMs adopts a proposed regional localizer generation (RLG) strategy to define a set of regional localizers and then derive them from a well-trained classifier. These regional localizers can be viewed as the base learner that only discerns region-wise object factors for localization tasks, and their results can be effectively weighted by our BagCAMs to form the final localization map. Experiments indicate that adopting our proposed BagCAMs can improve the performance of baseline WSOL methods to a great extent and obtains state-of-the-art performance on three WSOL benchmarks. Code are released at https://github.com/zh460045050/BagCAMs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images

Training deep models for RGB-D salient object detection (SOD) often requires a large number of labeled RGB-D images. However, RGB-D data is not easily acquired, which limits the development of RGB-D SOD techniques. To alleviate this issue, we present a Dual-Semi RGB-D Salient Object Detection Network (DS-Net) to leverage unlabeled RGB images for boosting RGB-D saliency detection. We first devise a depth decoupling convolutional neural network (DDCNN), which contains a depth estimation branch and a saliency detection branch. The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data. The saliency detection branch is used to fuse the RGB feature and depth feature to predict the RGB-D saliency. Then, the whole DDCNN is assigned as the backbone in a teacher-student framework for semi-supervised learning. Moreover, we also introduce a consistency loss on the intermediate attention and saliency maps for the unlabeled data, as well as a supervised depth and saliency loss for labeled data. Experimental results on seven widely-used benchmark datasets demonstrate that our DDCNN outperforms state-of-the-art methods both quantitatively and qualitatively. We also demonstrate that our semi-supervised DS-Net can further improve the performance, even when using an RGB image with the pseudo depth map.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation

In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can adaptively leverage the cluster assumption and consistency regularization of the unlabeled data according to the current learning status. This strategy can adaptively generate one-hot &#34;hard&#34; labels converted from task model predictions for better task model training. (2) For the unselected unlabeled images with low confidence, we introduce an Active learning (AL) algorithm to find the informative samples as the annotation candidates by exploiting virtual adversarial perturbation and model&#39;s density-aware entropy. These informative candidates are subsequently fed into the next training cycle for better SSL label propagation. Notably, the adaptive pseudo-labeling and informative active annotation form a learning closed-loop that are mutually collaborative to boost medical image SSL. To verify the effectiveness of the proposed method, we collected a metastatic epidural spinal cord compression (MESCC) dataset that aims to optimize MESCC diagnosis and classification for improved specialist referral and treatment. We conducted an extensive experimental study of BoostMIS on MESCC and another public dataset COVIDx. The experimental results verify our framework&#39;s effectiveness and generalisability for different medical image datasets with a significant improvement over various state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion

3D Multi-object tracking (MOT) ensures consistency during continuous dynamic detection, conducive to subsequent motion planning and navigation tasks in autonomous driving. However, camera-based methods suffer in the case of occlusions and it can be challenging to accurately track the irregular motion of objects for LiDAR-based methods. Some fusion methods work well but do not consider the untrustworthy issue of appearance features under occlusion. At the same time, the false detection problem also significantly affects tracking. As such, we propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT), which uses both camera and LiDAR data and significantly reduces tracking failures caused by occlusion and false detection. For occlusion problems, we are the first to propose an occlusion head to select the best object appearance features multiple times effectively, reducing the influence of occlusions. To decrease the impact of false detection in tracking, we design a motion cost matrix based on confidence scores which improve the positioning and object prediction accuracy in 3D space. As existing multi-object tracking methods only consider a single category, we also propose to build a multi-category loss to implement multi-object tracking in multi-category scenes. A series of validation experiments are conducted on the KITTI and nuScenes tracking benchmarks. Our proposed method achieves state-of-the-art performance and the lowest identity switches (IDS) value (23 for Car and 137 for Pedestrian) among all multi-modal MOT methods on the KITTI test dataset. And our proposed method achieves state-of-the-art performance among all algorithms on the nuScenes test dataset with 75.3% AMOTA.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning

Occlusion relationship reasoning based on convolution neural networks consists of two subtasks: occlusion boundary extraction and occlusion orientation inference. Due to the essential differences between the two subtasks in the feature expression at the higher and lower stages, it is challenging to carry on them simultaneously in one network. To address this issue, we propose a novel Dual-path Decoder Network, which uniformly extracts occlusion information at higher stages and separates into two paths to recover boundary and occlusion orientation respectively in lower stages. Besides, considering the restriction of occlusion orientation presentation to occlusion orientation learning, we design a new orthogonal representation for occlusion orientation and proposed the Orthogonal Orientation Regression loss which can get rid of the unfitness between occlusion representation and learning and further prompt the occlusion orientation learning. Finally, we apply a multi-scale loss together with our proposed orientation regression loss to guide the boundary and orientation path learning respectively. Experiments demonstrate that our proposed method achieves state-of-the-art results on PIOD and BSDS ownership datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Development of a compact high-resolution absolute gravity gradiometer based on atom interferometers

We present a compact high-resolution gravity gradiometer based on dual Rb-85 atom interferometers using stimulated Raman transitions. A baseline L=44.5 cm and an interrogation time T=130 ms are realized in a sensor head with volume of less than 100 liters. Experimental parameters are optimized to improve the short-term sensitivity while a rejection algorithm relying on inversion of the Raman wave vector is implemented to improve the long-term stability. After an averaging time of 17000 s, a phase resolution of 104 μrad is achieved, which corresponds to a gravity gradient resolution of 0.86 E. As far as we know, this is the sub-E atom gravity gradiometer with the highest level of compactness to date. After the evaluation and correction of system errors induced by light shift, residual Zeeman shift, Coriolis effect and self-attraction effect, the instrument serves as an absolute gravity gradiometer and with it the local gravity gradient is measured to be 3114 (53) E.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Harmonizer: Learning to Perform White-Box Image and Video Harmonization

Recent works on image harmonization solve the problem as a pixel-wise image translation task via large autoencoders. They have unsatisfactory performances and slow inference speeds when dealing with high-resolution images. In this work, we observe that adjusting the input arguments of basic image filters, e.g., brightness and contrast, is sufficient for humans to produce realistic images from the composite ones. Hence, we frame image harmonization as an image-level regression problem to learn the arguments of the filters that humans use for the task. We present a Harmonizer framework for image harmonization. Unlike prior methods that are based on black-box autoencoders, Harmonizer contains a neural network for filter argument prediction and several white-box filters (based on the predicted arguments) for image harmonization. We also introduce a cascade regressor and a dynamic loss strategy for Harmonizer to learn filter arguments more stably and precisely. Since our network only outputs image-level arguments and the filters we used are efficient, Harmonizer is much lighter and faster than existing methods. Comprehensive experiments demonstrate that Harmonizer surpasses existing methods notably, especially with high-resolution inputs. Finally, we apply Harmonizer to video harmonization, which achieves consistent results across frames and 56 fps at 1080P resolution. Code and models are available at: https://github.com/ZHKKKe/Harmonizer.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Motion Prediction via Joint Dependency Modeling in Phase Space

Motion prediction is a classic problem in computer vision, which aims at forecasting future motion given the observed pose sequence. Various deep learning models have been proposed, achieving state-of-the-art performance on motion prediction. However, existing methods typically focus on modeling temporal dynamics in the pose space. Unfortunately, the complicated and high dimensionality nature of human motion brings inherent challenges for dynamic context capturing. Therefore, we move away from the conventional pose based representation and present a novel approach employing a phase space trajectory representation of individual joints. Moreover, current methods tend to only consider the dependencies between physically connected joints. In this paper, we introduce a novel convolutional neural model to effectively leverage explicit prior knowledge of motion anatomy, and simultaneously capture both spatial and temporal information of joint trajectory dynamics. We then propose a global optimization module that learns the implicit relationships between individual joint features. Empirically, our method is evaluated on large-scale 3D human motion benchmark datasets (i.e., Human3.6M, CMU MoCap). These results demonstrate that our method sets the new state-of-the-art on the benchmark datasets. Our code will be available at https://github.com/Pose-Group/TEID.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-modal learning for predicting the genotype of glioma

The isocitrate dehydrogenase (IDH) gene mutation is an essential biomarker for the diagnosis and prognosis of glioma. It is promising to better predict glioma genotype by integrating focal tumor image and geometric features with brain network features derived from MRI. Convolutions neural networks show reasonable performance in predicting IDH mutation, which, however, cannot learn from non-Euclidean data, e.g., geometric and network data. In this study, we propose a multi-modal learning framework using three separate encoders to extract features of focal tumor image, tumor geometrics and global brain networks. To mitigate the limited availability of diffusion MRI, we develop a self-supervised approach to generate brain networks from anatomical multi-sequence MRI. Moreover, to extract tumor-related features from the brain network, we design a hierarchical attention module for the brain network encoder. Further, we design a bi-level multi-modal contrastive loss to align the multi-modal features and tackle the domain gap at the focal tumor and global brain. Finally, we propose a weighted population graph to integrate the multi-modal features for genotype prediction. Experimental results on the testing set show that the proposed model outperforms the baseline deep learning models. The ablation experiments validate the performance of different components of the framework. The visualized interpretation corresponds to clinical knowledge with further validation. In conclusion, the proposed learning framework provides a novel approach for predicting the genotype of glioma.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

NestedFormer: Nested Modality-Aware Transformer for Brain Tumor Segmentation

Multi-modal MR imaging is routinely used in clinical practice to diagnose and investigate brain tumors by providing rich complementary information. Previous multi-modal MRI segmentation methods usually perform modal fusion by concatenating multi-modal MRIs at an early/middle stage of the network, which hardly explores non-linear dependencies between modalities. In this work, we propose a novel Nested Modality-Aware Transformer (NestedFormer) to explicitly explore the intra-modality and inter-modality relationships of multi-modal MRIs for brain tumor segmentation. Built on the transformer-based multi-encoder and single-decoder structure, we perform nested multi-modal fusion for high-level representations of different modalities and apply modality-sensitive gating (MSG) at lower scales for more effective skip connections. Specifically, the multi-modal fusion is conducted in our proposed Nested Modality-aware Feature Aggregation (NMaFA) module, which enhances long-term dependencies within individual modalities via a tri-orientated spatial-attention transformer, and further complements key contextual information among modalities via a cross-modality attention transformer. Extensive experiments on BraTS2020 benchmark and a private meningiomas segmentation (MeniSeg) dataset show that the NestedFormer clearly outperforms the state-of-the-arts. The code is available at https://github.com/920232796/NestedFormer.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

RSCFed: Random Sampling Consensus Federated Semi-supervised Learning

Federated semi-supervised learning (FSSL) aims to derive a global model by training fully-labeled and fully-unlabeled clients or training partially labeled clients. The existing approaches work well when local clients have independent and identically distributed (IID) data but fail to generalize to a more practical FSSL setting, i.e., Non-IID setting. In this paper, we present a Random Sampling Consensus Federated learning, namely RSCFed, by considering the uneven reliability among models from fully-labeled clients, fully-unlabeled clients or partially labeled clients. Our key motivation is that given models with large deviations from either labeled clients or unlabeled clients, the consensus could be reached by performing random sub-sampling over clients. To achieve it, instead of directly aggregating local models, we first distill several sub-consensus models by random sub-sampling over clients and then aggregating the sub-consensus models to the global model. To enhance the robustness of sub-consensus models, we also develop a novel distance-reweighted model aggregation method. Experimental results show that our method outperforms state-of-the-art methods on three benchmarked datasets, including both natural and medical images. The code is available at https://github.com/XMed-Lab/RSCFed.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

spotFuzzer: Static Instrument and Fuzzing Windows COTs

The security research on Windows has received little attention in the academic circle. Most of the new methods are usually designed for Linux system, and are difficult to transplant to Windows. Fuzzing for Windows programs always suffering from its closed source. Therefore, we need to find an appropriate way to achieve feedback from Windows programs. To our knowledge, there are no stable and scalable static instrumentation tools for Windows yet, and dynamic tools, such as DynamoRIO, have been criticized for their performance. To make matters worse, dynamic instrumentation tools have very limited usage scenarios and are impotent for many system services or large commercial software. In this paper, we proposed spotInstr, a novel static tool for instrumenting Windows binaries. It is lightweight and can instrument most Windows PE programs in a very short time. At the same time, spotInstr provides a set of filters, which can be used to select instrumentation points or restrict the target regions. Based on these filters, we propose a novel memory-sensitive instrumentation method which can speed up both instrumentation and fuzzing. After that, we design a system called spotFuzzer, which leverage the ability of spotInstr and can fuzz most Windows binaries. We tested spotInstr and spotFuzzer in multiple dimensions to show their superior performance and stability.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Task-adaptive Asymmetric Deep Cross-modal Hashing

Supervised cross-modal hashing aims to embed the semantic correlations of heterogeneous modality data into the binary hash codes with discriminative semantic labels. Because of its advantages on retrieval and storage efficiency, it is widely used for solving efficient cross-modal retrieval. However, existing researches equally handle the different tasks of cross-modal retrieval, and simply learn the same couple of hash functions in a symmetric way for them. Under such circumstance, the uniqueness of different cross-modal retrieval tasks are ignored and sub-optimal performance may be brought. Motivated by this, we present a Task-adaptive Asymmetric Deep Cross-modal Hashing (TA-ADCMH) method in this paper. It can learn task-adaptive hash functions for two sub-retrieval tasks via simultaneous modality representation and asymmetric hash learning. Unlike previous cross-modal hashing approaches, our learning framework jointly optimizes semantic preserving that transforms deep features of multimedia data into binary hash codes, and the semantic regression which directly regresses query modality representation to explicit label. With our model, the binary codes can effectively preserve semantic correlations across different modalities, meanwhile, adaptively capture the query semantics. The superiority of TA-ADCMH is proved on two standard datasets from many aspects.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Time Interval-enhanced Graph Neural Network for Shared-account Cross-domain Sequential Recommendation

Shared-account Cross-domain Sequential Recommendation (SCSR) task aims to recommend the next item via leveraging the mixed user behaviors in multiple domains. It is gaining immense research attention as more and more users tend to sign up on different platforms and share accounts with others to access domain-specific services. Existing works on SCSR mainly rely on mining sequential patterns via Recurrent Neural Network (RNN)-based models, which suffer from the following limitations: 1) RNN-based methods overwhelmingly target discovering sequential dependencies in single-user behaviors. They are not expressive enough to capture the relationships among multiple entities in SCSR. 2) All existing methods bridge two domains via knowledge transfer in the latent space, and ignore the explicit cross-domain graph structure. 3) None existing studies consider the time interval information among items, which is essential in the sequential recommendation for characterizing different items and learning discriminative representations for them. In this work, we propose a new graph-based solution, namely TiDA-GCN, to address the above challenges. Specifically, we first link users and items in each domain as a graph. Then, we devise a domain-aware graph convolution network to learn userspecific node representations. To fully account for users&#39; domainspecific preferences on items, two effective attention mechanisms are further developed to selectively guide the message passing process. Moreover, to further enhance item- and account-level representation learning, we incorporate the time interval into the message passing, and design an account-aware self-attention module for learning items&#39; interactive characteristics. Experiments demonstrate the superiority of our proposed method from various aspects.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Weakly Supervised Object Localization as Domain Adaption

Weakly supervised object localization (WSOL) focuses on localizing objects only with the supervision of image-level classification masks. Most previous WSOL methods follow the classification activation map (CAM) that localizes objects based on the classification structure with the multi-instance learning (MIL) mechanism. However, the MIL mechanism makes CAM only activate discriminative object parts rather than the whole object, weakening its performance for localizing objects. To avoid this problem, this work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects. Under this perspective, a DA-WSOL pipeline is designed to better engage DA approaches into WSOL to enhance localization performance. It utilizes a proposed target sampling strategy to select different types of target samples. Based on these types of target samples, domain adaption localization (DAL) loss is elaborated. It aligns the feature distribution between the two domains by DA and makes the estimator perceive target domain cues by Universum regularization. Experiments show that our pipeline outperforms SOTA methods on multi benchmarks. Code are released at \url{https://github.com/zh460045050/DA-WSOL_CVPR2022}.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Deep Texture-Aware Features for Camouflaged Object Detection

Camouflaged object detection is a challenging task that aims to identify objects having similar texture to the surroundings. This paper presents to amplify the subtle texture difference between camouflaged objects and the background for camouflaged object detection by formulating multiple texture-aware refinement modules to learn the texture-aware features in a deep convolutional neural network. The texture-aware refinement module computes the covariance matrices of feature responses to extract the texture information, designs an affinity loss to learn a set of parameter maps that help to separate the texture between camouflaged objects and the background, and adopts a boundary-consistency loss to explore the object detail structures.We evaluate our network on the benchmark dataset for camouflaged object detection both qualitatively and quantitatively. Experimental results show that our approach outperforms various state-of-the-art methods by a large margin.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Large field-of-view non-invasive imaging through scattering layers using fluctuating random illumination

On-invasive optical imaging techniques are essential diagnostic tools in many fields. Although various recent methods have been proposed to utilize and control light in multiple scattering media, non-invasive optical imaging through and inside scattering layers across a large field of view remains elusive due to the physical limits set by the optical memory effect, especially without wavefront shaping techniques. Here, we demonstrate an approach that enables non-invasive fluorescence imaging behind scattering layers with field-of-views extending well beyond the optical memory effect. The method consists in demixing the speckle patterns emitted by a fluorescent object under variable unknown random illumination, using matrix factorization and a novel fingerprint-based reconstruction. Experimental validation shows the efficiency and robustness of the method with various fluorescent samples, covering a field of view up to three times the optical memory effect range. Our non-invasive imaging technique is simple, neither requires a spatial light modulator nor a guide star, and can be generalized to a wide range of incoherent contrast mechanisms and illumination schemes.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Optimization of graded filleted lattice structures subject to yield and buckling constraints

To reduce the stress concentration and ensure the structural safety for lattice structure designs, in this paper, a new optimization framework is developed for the optimal design of graded lattice structures, innovatively integrating fillet designs as well as yield and elastic buckling constraints. Both strut and fillet radii are defined as design variables. Homogenization method is employed to characterize the effective elastic constants and yield stresses of the lattice metamaterials. Metamaterial models are developed to represent the relationships between the metamaterial effective properties and lattice geometric variables. A yield constraint, based on the modified Hills yield criterion, is developed as a function of relative strut radii and fillet parameters. An elastic buckling constraint, based on the Euler buckling formula and the Johnson formula, is developed as a function of relative strut radii. Both yield and buckling constraints are integrated into an optimization problem formulation; a new optimization framework is proposed and a case study of minimizing the compliance of a Messerschmitt-Bolkow-Blohm beam is conducted. The yield and buckling constraints guarantee the safety of the optimized beams composed of BCC and PC lattices. Reductions in compliance and stress concentration are achieved by the optimized MBB beams.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Spectral Nonlocal Block for Neural Networks

The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks. Although having shown excellent performances, they lack the mechanism to encode the rich, structured information among elements in an image. In this paper, to theoretically analyze the property of these nonlocal-based blocks, we provide a unified approach to interpreting them, where we view them as a graph filter generated on a fully-connected graph. When the graph filter is approximated by Chebyshev polynomials, a generalized formulation can be derived for explaining the existing nonlocal-based blocks ($\mathit{e.g.,}$ nonlocal block, nonlocal stage, double attention block). Furthermore, we propose an efficient and robust spectral nonlocal block, which can be flexibly inserted into deep neural networks to catch the long-range dependencies between spatial pixels or temporal frames. Experimental results demonstrate the clear-cut improvements and practical applicabilities of the spectral nonlocal block on image classification (Cifar-10/100, ImageNet), fine-grained image classification (CUB-200), action recognition (UCF-101), and person re-identification (ILID-SVID, Mars, Prid-2011) tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A^2-GCN: An Attribute-aware Attentive GCN Model for Recommendation

As important side information, attributes have been widely exploited in the existing recommender system for better performance. In the real-world scenarios, it is common that some attributes of items/users are missing (e.g., some movies miss the genre data). Prior studies usually use a default value (i.e., &#34;other&#34;) to represent the missing attribute, resulting in sub-optimal performance. To address this problem, in this paper, we present an attribute-aware attentive graph convolution network (A${^2}$-GCN). In particular, we first construct a graph, whereby users, items, and attributes are three types of nodes and their associations are edges. Thereafter, we leverage the graph convolution network to characterize the complicated interactions among <users, items, attributes>. To learn the node representation, we turn to the message-passing strategy to aggregate the message passed from the other directly linked types of nodes (e.g., a user or an attribute). To this end, we are capable of incorporating associate attributes to strengthen the user and item representations, and thus naturally solve the attribute missing problem. Considering the fact that for different users, the attributes of an item have different influence on their preference for this item, we design a novel attention mechanism to filter the message passed from an item to a target user by considering the attribute information. Extensive experiments have been conducted on several publicly accessible datasets to justify our model. Results show that our model outperforms several state-of-the-art methods and demonstrate the effectiveness of our attention method.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Constrained Multi-shape Evolution for Overlapping Cytoplasm Segmentation

Segmenting overlapping cytoplasm of cells in cervical smear images is a clinically essential task, for quantitatively measuring cell-level features in order to diagnose cervical cancer. This task, however, remains rather challenging, mainly due to the deficiency of intensity (or color) information in the overlapping region. Although shape prior-based models that compensate intensity deficiency by introducing prior shape information (shape priors) about cytoplasm are firmly established, they often yield visually implausible results, mainly because they model shape priors only by limited shape hypotheses about cytoplasm, exploit cytoplasm-level shape priors alone, and impose no shape constraint on the resulting shape of the cytoplasm. In this paper, we present a novel and effective shape prior-based approach, called constrained multi-shape evolution, that segments all overlapping cytoplasms in the clump simultaneously by jointly evolving each cytoplasm&#39;s shape guided by the modeled shape priors. We model local shape priors (cytoplasm--level) by an infinitely large shape hypothesis set which contains all possible shapes of the cytoplasm. In the shape evolution, we compensate intensity deficiency for the segmentation by introducing not only the modeled local shape priors but also global shape priors (clump--level) modeled by considering mutual shape constraints of cytoplasms in the clump. We also constrain the resulting shape in each evolution to be in the built shape hypothesis set, for further reducing implausible segmentation results. We evaluated the proposed method in two typical cervical smear datasets, and the extensive experimental results show that the proposed method is effective to segment overlapping cytoplasm, consistently outperforming the state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DNF-Net: a Deep Normal Filtering Network for Mesh Denoising

This paper presents a deep normal filtering network, called DNF-Net, for mesh denoising. To better capture local geometry, our network processes the mesh in terms of local patches extracted from the mesh. Overall, DNF-Net is an end-to-end network that takes patches of facet normals as inputs and directly outputs the corresponding denoised facet normals of the patches. In this way, we can reconstruct the geometry from the denoised normals with feature preservation. Besides the overall network architecture, our contributions include a novel multi-scale feature embedding unit, a residual learning strategy to remove noise, and a deeply-supervised joint loss function. Compared with the recent data-driven works on mesh denoising, DNF-Net does not require manual input to extract features and better utilizes the training data to enhance its denoising performance. Finally, we present comprehensive experiments to evaluate our method and demonstrate its superiority over the state of the art on both synthetic and real-scanned meshes.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval

Social network stores and disseminates a tremendous amount of user shared images. Deep hashing is an efficient indexing technique to support large-scale social image retrieval, due to its deep representation capability, fast retrieval speed and low storage cost. Particularly, unsupervised deep hashing has well scalability as it does not require any manually labelled data for training. However, owing to the lacking of label guidance, existing methods suffer from severe semantic shortage when optimizing a large amount of deep neural network parameters. Differently, in this paper, we propose a Dual-level Semantic Transfer Deep Hashing (DSTDH) method to alleviate this problem with a unified deep hash learning framework. Our model targets at learning the semantically enhanced deep hash codes by specially exploiting the user-generated tags associated with the social images. Specifically, we design a complementary dual-level semantic transfer mechanism to efficiently discover the potential semantics of tags and seamlessly transfer them into binary hash codes. On the one hand, instance-level semantics are directly preserved into hash codes from the associated tags with adverse noise removing. Besides, an image-concept hypergraph is constructed for indirectly transferring the latent high-order semantic correlations of images and tags into hash codes. Moreover, the hash codes are obtained simultaneously with the deep representation learning by the discrete hash optimization strategy. Extensive experiments on two public social image retrieval datasets validate the superior performance of our method compared with state-of-the-art hashing methods. The source codes of our method can be obtained at https://github.com/research2020-1/DSTDH

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Enhancing Underexposed Photos using Perceptually Bidirectional Similarity

Although remarkable progress has been made, existing methods for enhancing underexposed photos tend to produce visually unpleasing results due to the existence of visual artifacts (e.g., color distortion, loss of details and uneven exposure). We observed that this is because they fail to ensure the perceptual consistency of visual information between the source underexposed image and its enhanced output. To obtain high-quality results free of these artifacts, we present a novel underexposed photo enhancement approach that is able to maintain the perceptual consistency. We achieve this by proposing an effective criterion, referred to as perceptually bidirectional similarity, which explicitly describes how to ensure the perceptual consistency. Particularly, we adopt the Retinex theory and cast the enhancement problem as a constrained illumination estimation optimization, where we formulate perceptually bidirectional similarity as constraints on illumination and solve for the illumination which can recover the desired artifact-free enhancement results. In addition, we describe a video enhancement framework that adopts the presented illumination estimation for handling underexposed videos. To this end, a probabilistic approach is introduced to propagate illuminations of sampled keyframes to the entire video by tackling a Bayesian Maximum A Posteriori problem. Extensive experiments demonstrate the superiority of our method over the state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Filament Intersections and Cold Dense Cores in Orion A North

We studied the filament structures and dense cores in OMC-2,3 region in Orion A North molecular cloud using the high-resolution N2H+ (1-0) spectral cube observed with the Atacama Large Millimeter/Submillimeter Array (ALMA). The filament network over a total length of 2 pc is found to contain 170 intersections and 128 candidate dense cores. The dense cores are all displaced from the infrared point sources (possible young stars), and the major fraction of cores (103) are located around the intersections. Towards the intersections, there is also an increasing trend for the total column density Ntot as well as the the power-law index of the column-density Probability Distribution Function (N-PDF), suggesting that the intersections would in general have more significant gas assembly than the other part of the filament paths. The virial analysis shows that the dense cores mostly have virial mass ratio of alpha_vir=M_vir/M_gas<1.0, suggesting them to be bounded by the self gravity. In the mean time, only about 23 percent of the cores have critical mass ratio of alpha_crit=M_crit/M_gas<1.0, suggesting them to be unstable against core collapse. Combining these results, it shows that the major fraction of the cold starless and possible prestellar cores in OMC-2,3 are being assembled around the intersections, and currently in a gravitationally bound state. But more extensive core collapse and star formation may still require continuous core-mass growth or other perturbatio

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Fusion-supervised Deep Cross-modal Hashing

Deep hashing has recently received attention in cross-modal retrieval for its impressive advantages. However, existing hashing methods for cross-modal retrieval cannot fully capture the heterogeneous multi-modal correlation and exploit the semantic information. In this paper, we propose a novel \emph{Fusion-supervised Deep Cross-modal Hashing} (FDCH) approach. Firstly, FDCH learns unified binary codes through a fusion hash network with paired samples as input, which effectively enhances the modeling of the correlation of heterogeneous multi-modal data. Then, these high-quality unified hash codes further supervise the training of the modality-specific hash networks for encoding out-of-sample queries. Meanwhile, both pair-wise similarity information and classification information are embedded in the hash networks under one stream framework, which simultaneously preserves cross-modal similarity and keeps semantic consistency. Experimental results on two benchmark datasets demonstrate the state-of-the-art performance of FDCH.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multi-Feature Discrete Collaborative Filtering for Fast Cold-start Recommendation

Hashing is an effective technique to address the large-scale recommendation problem, due to its high computation and storage efficiency on calculating the user preferences on items. However, existing hashing-based recommendation methods still suffer from two important problems: 1) Their recommendation process mainly relies on the user-item interactions and single specific content feature. When the interaction history or the content feature is unavailable (the cold-start problem), their performance will be seriously deteriorated. 2) Existing methods learn the hash codes with relaxed optimization or adopt discrete coordinate descent to directly solve binary hash codes, which results in significant quantization loss or consumes considerable computation time. In this paper, we propose a fast cold-start recommendation method, called Multi-Feature Discrete Collaborative Filtering (MFDCF), to solve these problems. Specifically, a low-rank self-weighted multi-feature fusion module is designed to adaptively project the multiple content features into binary yet informative hash codes by fully exploiting their complementarity. Additionally, we develop a fast discrete optimization algorithm to directly compute the binary hash codes with simple operations. Experiments on two public recommendation datasets demonstrate that MFDCF outperforms the state-of-the-arts on various aspects.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Resolution-dependent Subsonic Non-thermal Line Dispersion Revealed by ALMA

We report here Atacama Large Millimeter/submillimeter Array (ALMA) N$_2$H$^+$ (1-0) images of the Orion Molecular Cloud 2 and 3 (OMC-2/3) with high angular resolution (3&#39;&#39; or 1200 au) and high spatial dynamic range. Combining dataset from the ALMA main array, ALMA Compact Array (ACA), the Nobeyama 45m Telescope, and the JVLA (providing temperature measurement on matching scales), we find that most of the dense gas in OMC-2/3 is subsonic ($\rm σ_{NT}/c_{s}$ = 0.62) with a mean line width ($Δ\upsilon$) of 0.39 km s$^{-1}$ FWHM. This is markedly different from the majority of previous observations of massive star-forming regions. In contrast, line widths from the Nobeyama Telescope are transonic at 0.69 km s$^{-1}$ ($\rm σ_{NT}/c_{s}$ = 1.08). We demonstrated that the larger line widths obtained by the single-dish telescope arose from unresolved sub-structures within their respective beams. The dispersions from larger scales $σ_{ls}$ (as traced by the Nobeyama Telescope) can be decomposed into three components $\rm σ_{ls}^2 = σ_{ss}^2+ σ_{bm}^2+ σ_{rd}^2$, where small-scale $σ_{ss}$ is the line dispersion of each ALMA beam, bulk motion $σ_{bm}$ is dispersion between peak velocity of each ALMA beam, and $σ_{rd}$ is the residual dispersion. Such decomposition, though purely empirical, appears to be robust throughout our data cubes. Apparent supersonic line widths, commonly found in massive molecular clouds, are thus likely due to the effect of poor spatial resolution. The observed non-thermal line dispersion (sometimes referred to as &#39;turbulence&#39;) transits from supersonic to subsonic at $\sim 0.05$ pc scales in OMC-2/3 region. Such transition could be commonly found with sufficient spatial (not just angular) resolution, even in regions with massive young clusters, such as Orion molecular clouds studied here.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Robust Medical Instrument Segmentation Challenge 2019

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

SAC-Net: Spatial Attenuation Context for Salient Object Detection

This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects. Our key idea is to adaptively propagate and aggregate the image context features with variable attenuation over the entire feature maps. To achieve this, we design the spatial attenuation context (SAC) module to recurrently translate and aggregate the context features independently with different attenuation factors and then to attentively learn the weights to adaptively integrate the aggregated context features. By further embedding the module to process individual layers in a deep network, namely SAC-Net, we can train the network end-to-end and optimize the context features for detecting salient objects. Compared with 29 state-of-the-art methods, experimental results show that our method performs favorably over all the others on six common benchmark data, both quantitatively and visually.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Three dimensional projection effects on chemistry in a Planck galactic cold clump

Offsets of molecular line emission peaks from continuum peaks are very common but frequently difficult to explain with a single spherical cloud chemical model. We propose that the spatial projection effects of an irregular three dimensional (3D) cloud structure can be a solution. This work shows that the idea can be successfully applied to the Planck cold clump G224.4-0.6 by approximating it with four individual spherically symmetric cloud cores whose chemical patterns overlap with each other to produce observable line maps. With the empirical physical structures inferred from the observation data of this clump and a gas-grain chemical model, the four cores can satisfactorily reproduce its 850 $μ$m continuum map and the diverse peak offsets of CCS, HC$_3$N and N$_2$H$^+$ simultaneously at chemical ages of about $8\times 10^5\sim 3\times 10^6$ yrs. The 3D projection effects on chemistry has the potential to explain such asymmetrical distributions of chemicals in many other molecular clouds.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Self-Tuning Parameter Servers

Recent years, many applications have been driven advances by the use of Machine Learning (ML). Nowadays, it is common to see industrial-strength machine learning jobs that involve millions of model parameters, terabytes of training data, and weeks of training. Good efficiency, i.e., fast completion time of running a specific ML job, therefore, is a key feature of a successful ML system. While the completion time of a long-running ML job is determined by the time required to reach model convergence, practically that is also largely influenced by the values of various system settings. In this paper, we contribute techniques towards building self-tuning parameter servers. Parameter Server (PS) is a popular system architecture for large-scale machine learning systems; and by self-tuning we mean while a long-running ML job is iteratively training the expert-suggested model, the system is also iteratively learning which system setting is more efficient for that job and applies it online. While our techniques are general enough to various PS-style ML systems, we have prototyped our techniques on top of TensorFlow. Experiments show that our techniques can reduce the completion times of a variety of long-running TensorFlow jobs from 1.4x to 18x.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Direction-aware Spatial Context Features for Shadow Detection and Removal

Shadow detection and shadow removal are fundamental and challenging tasks, requiring an understanding of the global image semantics. This paper presents a novel deep neural network design for shadow detection and removal by analyzing the spatial image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting and removing shadows. This design is developed into the DSC module and embedded in a convolutional neural network (CNN) to learn the DSC features at different levels. Moreover, we design a weighted cross entropy loss to make effective the training for shadow detection and further adopt the network for shadow removal by using a Euclidean loss function and formulating a color transfer function to address the color and luminosity inconsistencies in the training pairs. We employed two shadow detection benchmark datasets and two shadow removal benchmark datasets, and performed various experiments to evaluate our method. Experimental results show that our method performs favorably against the state-of-the-art methods for both shadow detection and shadow removal.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

ZAIGA: Zhaoshan Long-baseline Atom Interferometer Gravitation Antenna

The Zhaoshan long-baseline Atom Interferometer Gravitation Antenna (ZAIGA) is a new type of underground laser-linked interferometer facility, and is currently under construction. It is in the 200-meter-on-average underground of a mountain named Zhaoshan which is about 80 km southeast to Wuhan. ZAIGA will be equipped with long-baseline atom interferometers, high-precision atom clocks, and large-scale gyros. ZAIGA facility will take an equilateral triangle configuration with two 1-km-apart atom interferometers in each arm, a 300-meter vertical tunnel with atom fountain and atom clocks mounted, and a tracking-and-ranging 1-km-arm-length prototype with lattice optical clocks linked by locked lasers. The ZAIGA facility will be used for experimental research on gravitation and related problems including gravitational wave detection, high-precision test of the equivalence principle of micro-particles, clock based gravitational red-shift measurement, rotation measurement and gravito-magnetic effect.

0 citations0 reviewsNo code linkedOpen access
preprint2018arXiv

Direction-aware Spatial Context Features for Shadow Detection

Shadow detection is a fundamental and challenging task, since it requires an understanding of global image semantics and there are various backgrounds around shadows. This paper presents a novel network for shadow detection by analyzing image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting shadows. This design is developed into the DSC module and embedded in a CNN to learn DSC features at different levels. Moreover, a weighted cross entropy loss is designed to make the training more effective. We employ two common shadow detection benchmark datasets and perform various experiments to evaluate our network. Experimental results show that our network outperforms state-of-the-art methods and achieves 97% accuracy and 38% reduction on balance error rate.

0 citations0 reviewsNo code linkedOpen access